Iterative Search for Weakly Supervised Semantic Parsing

Pradeep Dasigi, Matt Gardner, Shikhar Murty, Luke Zettlemoyer, Eduard Hovy
2019 Proceedings of the 2019 Conference of the North  
Training semantic parsers from questionanswer pairs typically involves searching over an exponentially large space of logical forms, and an unguided search can easily be misled by spurious logical forms that coincidentally evaluate to the correct answer. We propose a novel iterative training algorithm that alternates between searching for consistent logical forms and maximizing the marginal likelihood of the retrieved ones. This training scheme lets us iteratively train models that provide
more » ... s that provide guidance to subsequent ones to search for logical forms of increasing complexity, thus dealing with the problem of spuriousness. We evaluate these techniques on two hard datasets: WIKITABLEQUESTIONS (WTQ) and Cornell Natural Language Visual Reasoning (NLVR), and show that our training algorithm outperforms the previous best systems, on WTQ in a comparable setting, and on NLVR with significantly less supervision.
doi:10.18653/v1/n19-1273 dblp:conf/naacl/Dasigi0MZH19 fatcat:ow7ygq7sqbdwjdmcw2bbwgbdqa